Instructions to use DeepGlint-AI/UniME-LLaVA-OneVision-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DeepGlint-AI/UniME-LLaVA-OneVision-7B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="DeepGlint-AI/UniME-LLaVA-OneVision-7B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("DeepGlint-AI/UniME-LLaVA-OneVision-7B")
model = AutoModelForImageTextToText.from_pretrained("DeepGlint-AI/UniME-LLaVA-OneVision-7B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DeepGlint-AI/UniME-LLaVA-OneVision-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DeepGlint-AI/UniME-LLaVA-OneVision-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeepGlint-AI/UniME-LLaVA-OneVision-7B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/DeepGlint-AI/UniME-LLaVA-OneVision-7B

SGLang

How to use DeepGlint-AI/UniME-LLaVA-OneVision-7B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "DeepGlint-AI/UniME-LLaVA-OneVision-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeepGlint-AI/UniME-LLaVA-OneVision-7B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "DeepGlint-AI/UniME-LLaVA-OneVision-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeepGlint-AI/UniME-LLaVA-OneVision-7B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use DeepGlint-AI/UniME-LLaVA-OneVision-7B with Docker Model Runner:
```
docker model run hf.co/DeepGlint-AI/UniME-LLaVA-OneVision-7B
```

Update pipeline tag to zero-shot-image-classification

by nielsr HF Staff - opened Aug 6, 2025

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+10

-7

Update pipeline tag to zero-shot-image-classificationc071f98b

nielsr

Aug 6, 2025

This PR updates the pipeline_tag in the model card from image-text-to-text to zero-shot-image-classification.

The paper abstract states that UniME learns "discriminative representations for diverse downstream tasks," particularly for "image-text retrieval and clustering." The quick start guide also demonstrates computing a similarity score between image and text embeddings. This functionality is more aligned with discriminative tasks like zero-shot classification and retrieval rather than text generation or translation.

Changing the pipeline_tag will improve the model's discoverability on the Hugging Face Hub, allowing users to find it under the most relevant category for its primary use case.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment